In [17]:
#Most used words in wine description for each point
from wordcloud import WordCloud, STOPWORDS, ImageColorGenerator
import string
import re
import matplotlib as mpl
import matplotlib.pyplot as plt
import nltk.corpus
#nltk.download('stopwords')
from nltk.corpus import stopwords
#Function to clean the description
def cleanDescription(description):
#remove punctuation
description = description.translate(str.maketrans('', '', string.punctuation))
#remove number
description = re.sub(r'\d+', '', description)
#remove space
description = description.strip()
#remove stopword
description = [word for word in description.split() if word not in stopwords.words('english')]
#remove short word
description = [word for word in description if len(word) > 2]
#remove word with number
description = [word for word in description if not any(c.isdigit() for c in word)]
#remove word with special character
description = [word for word in description if not any(c in string.punctuation for c in word)]
#remove string The (trivial word)
description = [word for word in description if not word == 'The']
#remove string Wine (trivial word)
description = [word for word in description if not word == 'Wine']
description = [word for word in description if not word == 'wine']
#remove string This (trivial word)
description = [word for word in description if not word == 'This']
#remove word with underscore
description = [word for word in description if not any(c == '_' for c in word)]
#remove word with dash
description = [word for word in description if not any(c == '-' for c in word)]
#remove word with slash
description = [word for word in description if not any(c == '/' for c in word)]
#remove word with backslash
description = [word for word in description if not any(c == '\\' for c in word)]
#remove word with dot
description = [word for word in description if not any(c == '.' for c in word)]
#remove word with comma
description = [word for word in description if not any(c == ',' for c in word)]
#remove word with colon
description = [word for word in description if not any(c == ':' for c in word)]
#remove word with semicolon
description = [word for word in description if not any(c == ';' for c in word)]
#remove word with exclamation mark
description = [word for word in description if not any(c == '!' for c in word)]
#remove word with question mark
description = [word for word in description if not any(c == '?' for c in word)]
return description
#Function to create the wordcloud
def createWordCloud(description, title):
#create wordcloud
wordcloud = WordCloud(width = 500, height = 500,
min_font_size = 10,
background_color ='white').generate(description)
# plot the WordCloud image
#plt.figure(figsize = (25,25), facecolor = None)
plt.imshow(wordcloud)
plt.axis("off")
plt.tight_layout(pad = 0)
#plt.title(title, fontsize=50)
plt.show()
#Function to create the wordcloud for each point
def createWordCloudForPoint(df, pointsDescription):
#filter by point
dfPoint = df.loc[df['pointsDescription'] == pointsDescription]
#clean description
dfPoint['description'] = dfPoint['description'].apply(lambda x: cleanDescription(x))
#join all the description
description = ''.join(' '.join(l) for l in dfPoint['description'].values)
########################
#Remove the comment below to save in a dataframe the most used word for each point
#find most 10 used word in the description save it in a dataframe
#dfMostUsedWord = pd.DataFrame(description.split(), columns=['word']).word.value_counts().reset_index().rename(columns={'index':'word', 'word':'count'}).head(10)
#print(point)
#display(dfMostUsedWord)
########################
#create wordcloud
createWordCloud(description, 'Most used words of \'' + str(pointsDescription) + '\' category')
#remove warning
pd.set_option('mode.chained_assignment', None)
#Create wordcloud for each point
for point in set(df['pointsDescription']):
print(point)
createWordCloudForPoint(df, point)
#reset warning
pd.reset_option('mode.chained_assignment')
Acceptable
Good
Classic
Very good
Superb
Excellent
